vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

examples : replace llama_kv_cache_seq_* with llama_past_seq_*

Browse source
This commit is contained in:
Francis Couture-Harpin 2024-06-10 14:44:42 -04:00
parent 372482dffe
commit 43d8d4bf9e
23 changed files with 125 additions and 112 deletions
Download patch file Download diff file Expand all files Collapse all files

3
examples/lookup/lookup.cpp
View file

@ -195,7 +195,8 @@ int main(int argc, char ** argv){
// KV cache management
// clean the cache of draft tokens that weren't accepted
llama_kv_cache_seq_rm(ctx, 0, n_past, -1);
// FIXME: recurrent and hybrid models
llama_past_seq_rm(ctx, 0, n_past, -1);
llama_batch_clear(batch_tgt);
llama_batch_add(batch_tgt, draft[0], n_past, { 0 }, true);